Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 116
    Prev
    Next
    INDEX
    Explanations

    train word problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scoop
    -0.09
     scoop
    -0.08
     avere
    -0.08
     GRAND
    -0.08
     sjá
    -0.07
     تقييم
    -0.07
     avaliar
    -0.07
     obviamente
    -0.07
     ''↵
    -0.07
     veliki
    -0.07
    POSITIVE LOGITS
    -result
    0.08
    326
    0.08
    -Bahn
    0.08
    _GRAPH
    0.08
    平方米
    0.08
    ированы
    0.08
    663
    0.08
    _PHY
    0.07
    .Cryptography
    0.07
     emerged
    0.07
    Activations Density 0.005%

    No Known Activations